Pith. sign in

Gonçalo Paulo, Stepan Shabalin, and Nora Belrose

2 Pith papers cite this work. Polarity classification is still indexing.

2 Pith papers citing it

citation-role summary

background 2

citation-polarity summary

fields

cs.LG 2

years

2026 1 2025 1

verdicts

UNVERDICTED 2

roles

background 1

polarities

background 1

representative citing papers

WriteSAE: Sparse Autoencoders for Recurrent State

cs.LG · 2026-05-12 · unverdicted · novelty 8.0 · 3 refs

WriteSAE introduces sparse autoencoders with rank-1 matrix atoms for recurrent state updates, allowing replacement tests that outperform deletion on 92.4% of positions and a formula predicting logit changes with R²=0.98.

citing papers explorer

Showing 2 of 2 citing papers.

  • WriteSAE: Sparse Autoencoders for Recurrent State cs.LG · 2026-05-12 · unverdicted · none · ref 16 · 3 links

    WriteSAE introduces sparse autoencoders with rank-1 matrix atoms for recurrent state updates, allowing replacement tests that outperform deletion on 92.4% of positions and a formula predicting logit changes with R²=0.98.

  • Open Problems in Mechanistic Interpretability cs.LG · 2025-01-27 · unverdicted · none · ref 10

    A review paper that organizes conceptual, practical, and socio-technical open problems in mechanistic interpretability.